org.deeplearning4j.util

Class ConvolutionUtils

java.lang.Object

org.deeplearning4j.util.ConvolutionUtils

public class ConvolutionUtils
extends Object

Convolutional shape utilities

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
static org.nd4j.linalg.api.ndarray.INDArray	adapt2dMask(org.nd4j.linalg.api.ndarray.INDArray mask, org.nd4j.linalg.api.ndarray.INDArray output, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static int[]	effectiveKernelSize(int[] kernel, int[] dilation)
static int[]	getDeconvolutionOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation) Get the output size of a deconvolution operation for given input data.
static int[]	getHeightAndWidth(int[] shape) Get the height and width for an image
static int[]	getHeightAndWidth(NeuralNetConfiguration conf) Get the height and width from the configuration
static int[]	getHWDFromInputType(InputType inputType) Get heigh/width/channels as length 3 int[] from the InputType
static int[]	getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode)
static int[]	getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation) Get the output size (height/width) for the given input data and CNN configuration
static int[]	getSameModeBottomRightPadding(int[] outSize, int[] inSize, int[] kernel, int[] strides, int[] dilation) Get bottom and right padding for same mode only.
static int[]	getSameModeTopLeftPadding(int[] outSize, int[] inSize, int[] kernel, int[] strides, int[] dilation) Get top and left padding for same mode only.
static int	numChannels(int[] shape) Returns the number of feature maps for a given shape (must be at least 3 dimensions
static int	numFeatureMap(NeuralNetConfiguration conf)
static org.nd4j.linalg.api.ndarray.INDArray	reshape2dTo4d(org.nd4j.linalg.api.ndarray.INDArray in2d, int[] toShape, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static org.nd4j.linalg.api.ndarray.INDArray	reshape3dMask(org.nd4j.linalg.api.ndarray.INDArray mask, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static org.nd4j.linalg.api.ndarray.INDArray	reshape4dMask(org.nd4j.linalg.api.ndarray.INDArray mask, LayerWorkspaceMgr workspaceMgr, ArrayType arrayType)
static org.nd4j.linalg.api.ndarray.INDArray	reshape4dTo2d(org.nd4j.linalg.api.ndarray.INDArray in, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static org.nd4j.linalg.api.ndarray.INDArray	reshapeMaskIfRequired(org.nd4j.linalg.api.ndarray.INDArray mask, org.nd4j.linalg.api.ndarray.INDArray output, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static void	validateCnnKernelStridePadding(int[] kernelSize, int[] stride, int[] padding) Perform validation on the CNN layer kernel/stride/padding.
static void	validateConvolutionModePadding(ConvolutionMode mode, int[] padding) Check that the convolution mode is consistent with the padding specification
static void	validateShapes(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] eKernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation, int[] inShape, boolean atrous)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

getOutputSize

public static int[] getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                  int[] kernel,
                                  int[] strides,
                                  int[] padding,
                                  ConvolutionMode convolutionMode)

getDeconvolutionOutputSize

public static int[] getDeconvolutionOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                               int[] kernel,
                                               int[] strides,
                                               int[] padding,
                                               ConvolutionMode convolutionMode,
                                               int[] dilation)

Get the output size of a deconvolution operation for given input data. In deconvolution, we compute the inverse of the shape computation of a convolution.

Parameters:

inputData - Input data

kernel - Kernel size (height/width)

strides - Strides (height/width)

padding - Padding (height/width)

convolutionMode - Convolution mode (Same, Strict, Truncate)

dilation - Kernel dilation (height/width)

Returns:

Output size: int[2] with output height/width

getOutputSize

public static int[] getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                  int[] kernel,
                                  int[] strides,
                                  int[] padding,
                                  ConvolutionMode convolutionMode,
                                  int[] dilation)

Get the output size (height/width) for the given input data and CNN configuration

Parameters:

inputData - Input data

kernel - Kernel size (height/width)

strides - Strides (height/width)

padding - Padding (height/width)

convolutionMode - Convolution mode (Same, Strict, Truncate)

dilation - Kernel dilation (height/width)

Returns:

Output size: int[2] with output height/width

validateShapes

public static void validateShapes(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                  int[] eKernel,
                                  int[] strides,
                                  int[] padding,
                                  ConvolutionMode convolutionMode,
                                  int[] dilation,
                                  int[] inShape,
                                  boolean atrous)

effectiveKernelSize

public static int[] effectiveKernelSize(int[] kernel,
                                        int[] dilation)

getSameModeTopLeftPadding

public static int[] getSameModeTopLeftPadding(int[] outSize,
                                              int[] inSize,
                                              int[] kernel,
                                              int[] strides,
                                              int[] dilation)

Get top and left padding for same mode only.

Parameters:

outSize - Output size (length 2 array, height dimension first)

inSize - Input size (length 2 array, height dimension first)

kernel - Kernel size (length 2 array, height dimension first)

strides - Strides (length 2 array, height dimension first)

dilation - Dilation (length 2 array, height dimension first)

Returns:

Top left padding (length 2 array, height dimension first)

getSameModeBottomRightPadding

public static int[] getSameModeBottomRightPadding(int[] outSize,
                                                  int[] inSize,
                                                  int[] kernel,
                                                  int[] strides,
                                                  int[] dilation)

Get bottom and right padding for same mode only.

Parameters:

outSize - Output size (length 2 array, height dimension first)

inSize - Input size (length 2 array, height dimension first)

kernel - Kernel size (length 2 array, height dimension first)

strides - Strides (length 2 array, height dimension first)

dilation - Dilation (length 2 array, height dimension first)

Returns:

Bottom right padding (length 2 array, height dimension first)

getHeightAndWidth

public static int[] getHeightAndWidth(NeuralNetConfiguration conf)

Get the height and width from the configuration

Parameters:

conf - the configuration to get height and width from

Returns:

the configuration to get height and width from

numFeatureMap

public static int numFeatureMap(NeuralNetConfiguration conf)

Parameters:

conf - the configuration to get the number of kernels from

Returns:

the number of kernels/filters to apply

getHeightAndWidth

public static int[] getHeightAndWidth(int[] shape)

Get the height and width for an image

Parameters:

shape - the shape of the image

Returns:

the height and width for the image

numChannels

public static int numChannels(int[] shape)

Returns the number of feature maps for a given shape (must be at least 3 dimensions

Parameters:

shape - the shape to get the number of feature maps for

Returns:

the number of feature maps for a particular shape

validateConvolutionModePadding

public static void validateConvolutionModePadding(ConvolutionMode mode,
                                                  int[] padding)

Check that the convolution mode is consistent with the padding specification

validateCnnKernelStridePadding

public static void validateCnnKernelStridePadding(int[] kernelSize,
                                                  int[] stride,
                                                  int[] padding)

Perform validation on the CNN layer kernel/stride/padding. Expect 2d int[], with values > 0 for kernel size and stride, and values >= 0 for padding.

Parameters:

kernelSize - Kernel size array to check

stride - Stride array to check

padding - Padding array to check

reshape4dTo2d

public static org.nd4j.linalg.api.ndarray.INDArray reshape4dTo2d(org.nd4j.linalg.api.ndarray.INDArray in,
                                                                 LayerWorkspaceMgr workspaceMgr,
                                                                 ArrayType type)

reshape2dTo4d

public static org.nd4j.linalg.api.ndarray.INDArray reshape2dTo4d(org.nd4j.linalg.api.ndarray.INDArray in2d,
                                                                 int[] toShape,
                                                                 LayerWorkspaceMgr workspaceMgr,
                                                                 ArrayType type)

reshapeMaskIfRequired

public static org.nd4j.linalg.api.ndarray.INDArray reshapeMaskIfRequired(org.nd4j.linalg.api.ndarray.INDArray mask,
                                                                         org.nd4j.linalg.api.ndarray.INDArray output,
                                                                         LayerWorkspaceMgr workspaceMgr,
                                                                         ArrayType type)

adapt2dMask

public static org.nd4j.linalg.api.ndarray.INDArray adapt2dMask(org.nd4j.linalg.api.ndarray.INDArray mask,
                                                               org.nd4j.linalg.api.ndarray.INDArray output,
                                                               LayerWorkspaceMgr workspaceMgr,
                                                               ArrayType type)

reshape3dMask

public static org.nd4j.linalg.api.ndarray.INDArray reshape3dMask(org.nd4j.linalg.api.ndarray.INDArray mask,
                                                                 LayerWorkspaceMgr workspaceMgr,
                                                                 ArrayType type)

reshape4dMask

public static org.nd4j.linalg.api.ndarray.INDArray reshape4dMask(org.nd4j.linalg.api.ndarray.INDArray mask,
                                                                 LayerWorkspaceMgr workspaceMgr,
                                                                 ArrayType arrayType)

getHWDFromInputType

public static int[] getHWDFromInputType(InputType inputType)

Get heigh/width/channels as length 3 int[] from the InputType

Parameters:

inputType - Input type to get

Returns:

Length